This collection contains datasets and models related to "BLEUBERI: BLEU is a surprisingly effective reward for instruction following".
Yapei Chang PRO
yapeichang
AI & ML interests
NLP
Recent Activity
upvoted a paper 4 days ago
World of SWECraft: Agent Collaboration at Scale via Simulated Software Worlds updated a dataset 10 days ago
yapeichang/PostMark published a dataset 10 days ago
yapeichang/PostMarkOrganizations
models 42
yapeichang/memo-32b-4tier
32B • Updated • 4
yapeichang/memo-7b-4tier-50B-preserved
7B • Updated • 4
yapeichang/memo-7b-4tier
7B • Updated • 6
yapeichang/grpo_olmo3_pretrain_sft_ckpt_80pct
528k • Updated • 3
yapeichang/sft_olmo3_pretrain_ckpt_80pct
Updated • 4
yapeichang/grpo_olmo3_pretrain_sft_ckpt_10pct
528k • Updated • 5
yapeichang/grpo_olmo3_pretrain_sft_ckpt_25pct
528k • Updated • 5
yapeichang/grpo_olmo3_pretrain_sft_ckpt_50pct
528k • Updated • 4
yapeichang/grpo_olmo3_pretrain_sft_ckpt_100pct
528k • Updated • 8
yapeichang/memo-7b
7B • Updated • 7
datasets 5
yapeichang/PostMark
Updated • 53
yapeichang/WebOrganizer-format-topic-merged-Llama-3.1-8B
Viewer • Updated • 1M • 18
yapeichang/WebOrganizer-format-topic-merged-Llama-3.1-405B-FP8
Viewer • Updated • 100k • 21
yapeichang/hotpotqa-filtered
Viewer • Updated • 5.31k • 22
yapeichang/BLEUBERI-Tulu3-50k
Viewer • Updated • 50k • 32 • 2